diff --git a/README.md b/README.md index f609953..34cedc9 100644 --- a/README.md +++ b/README.md @@ -11,17 +11,18 @@ Workflows for validating sequence data - Set of .txt files containing the validation reports, one per input file ### Cromwell version support - - Successfully tested on v33 + - Successfully tested on v49 - Does not work on versions < v23 due to output syntax -### Important Note : -- The provided JSON is meant to be a ready to use example JSON template of the workflow. It is the user’s responsibility to correctly set the reference and resource input variables using the [GATK Tool and Tutorial Documentations](https://software.broadinstitute.org/gatk/documentation/). -- Relevant reference and resources bundles can be accessed in [Resource Bundle](https://software.broadinstitute.org/gatk/download/bundle). +### Important Notes : - Runtime parameters are optimized for Broad's Google Cloud Platform implementation. +- The provided JSON is a ready to use example JSON template of the workflow. Users are responsible for reviewing the [GATK Tool and Tutorial Documentations](https://gatk.broadinstitute.org/hc/en-us/categories/360002310591) to properly set the reference and resource variables. - For help running workflows on the Google Cloud Platform or locally please -view the following tutorial [(How to) Execute Workflows from the gatk-workflows Git Organization](https://software.broadinstitute.org/gatk/documentation/article?id=12521). -- The following material is provided by the GATK Team. Please post any questions or concerns to one of our forum sites : [GATK](https://gatkforums.broadinstitute.org/gatk/categories/ask-the-team/) , [FireCloud](https://gatkforums.broadinstitute.org/firecloud/categories/ask-the-firecloud-team) or [Terra](https://broadinstitute.zendesk.com/hc/en-us/community/topics/360000500432-General-Discussion) , [WDL/Cromwell](https://gatkforums.broadinstitute.org/wdl/categories/ask-the-wdl-team). -- Please visit the [User Guide](https://software.broadinstitute.org/gatk/documentation/) site for further documentation on our workflows and tools. +view the following tutorial [(How to) Execute Workflows from the gatk-workflows Git Organization](https://gatk.broadinstitute.org/hc/en-us/articles/360035530952). +- Relevant reference and resources bundles can be accessed in [Resource Bundle](https://gatk.broadinstitute.org/hc/en-us/articles/360036212652). + +### Contact Us : +- The following material is provided by the Data Science Platforum group at the Broad Institute. Please direct any questions or concerns to one of our forum sites : [GATK](https://gatk.broadinstitute.org/hc/en-us/community/topics) or [Terra](https://support.terra.bio/hc/en-us/community/topics/360000500432). ### LICENSING : Copyright Broad Institute, 2019 | BSD-3 diff --git a/validate-bam.inputs.json b/validate-bam.inputs.json index 3a5203f..bf7ffc5 100644 --- a/validate-bam.inputs.json +++ b/validate-bam.inputs.json @@ -1,15 +1,6 @@ { - "##Comment1":"Input", "ValidateBamsWf.bam_array": [ "gs://gatk-test-data/wgs_bam/NA12878_24RG_hg38/NA12878_24RG_small.hg38.bam", "gs://gatk-test-data/wgs_bam/NA12878_24RG_hg38/NA12878_24RG_med.hg38.bam" - ], - "##Comment2":"Parameter", - "#ValidateBamsWf.ValidateBAM.validation_mode": "String (optional)", - - "##Comment3":"Runtime - uncomment the lines below and supply a valid docker container to override the default", - "#ValidateBamsWf.ValidateBAM.machine_mem_gb": "Int? (optional)", - "#ValidateBamsWf.ValidateBAM.disk_space_gb": "Int? (optional)", - "#ValidateBamsWf.ValidateBAM.gatk_path_override": "String (optional)", - "#ValidateBamsWf.gatk_docker_override": "String (optional)" + ] } \ No newline at end of file diff --git a/validate-bam.wdl b/validate-bam.wdl index 492ed73..9b13ecd 100644 --- a/validate-bam.wdl +++ b/validate-bam.wdl @@ -1,3 +1,4 @@ +version 1.0 ## Copyright Broad Institute, 2017 ## ## This WDL performs format validation on SAM/BAM files in a list @@ -26,11 +27,11 @@ # WORKFLOW DEFINITION workflow ValidateBamsWf { - Array[File] bam_array - String? gatk_docker_override - String gatk_docker = select_first([gatk_docker_override, "broadinstitute/gatk:latest"]) - String? gatk_path_override - String gatk_path = select_first([gatk_path_override, "/gatk/gatk"]) + input { + Array[File] bam_array + String gatk_docker = "broadinstitute/gatk:latest" + String gatk_path = "/gatk/gatk" + } # Process the input files in parallel scatter (input_bam in bam_array) { @@ -58,18 +59,20 @@ workflow ValidateBamsWf { # Validate a SAM or BAM using Picard ValidateSamFile task ValidateBAM { - # Command parameters - File input_bam - String output_basename - String? validation_mode - String gatk_path + input { + # Command parameters + File input_bam + String output_basename + String? validation_mode + String gatk_path - # Runtime parameters - String docker - Int? machine_mem_gb - Int? disk_space_gb - Int disk_size = ceil(size(input_bam, "GB")) + 20 - + # Runtime parameters + String docker + Int machine_mem_gb = 4 + Int addtional_disk_space_gb = 50 + } + + Int disk_size = ceil(size(input_bam, "GB")) + addtional_disk_space_gb String output_name = "${output_basename}_${validation_mode}.txt" command { @@ -81,9 +84,8 @@ task ValidateBAM { } runtime { docker: docker - memory: select_first([machine_mem_gb, 1]) + " GB" - cpu: "1" - disks: "local-disk " + select_first([disk_space_gb, disk_size]) + " HDD" + memory: machine_mem_gb + " GB" + disks: "local-disk " + disk_size + " HDD" } output { File validation_report = "${output_name}"